We propose a committee-based active learning method for large vocabulary continuous speech recognition. In this approach, multiple recognizers are prepared beforehand, and the rec...
Recognizing commonly used data structures and algorithms is a key activity in reverse engineering. Systems developed to automate this recognition process have been isolated, stand...
In this paper we present a novel approach to continuous, whole-sentence ASL recognition that uses phonemes instead of whole signs as the basic units. Our approach is based on a se...
We present an active learning approach to choose image annotation requests among both object category labels and the objects’ attribute labels. The goal is to solicit those labe...
The design of a general purpose artificial vision system capable of recognizing arbitrarily complex threedimensional objects without human intervention is still a challenging task...